Mask-RCNN代码实现（简述）

（1）代码地址：https://github.com/matterport/Mask_RCNN

（2）安装主要按照上面网址的说明进行，下面就我做的修改和遇到的问题记录如下：

1、由于之前安装了tensorflow1.4(带GPU),所以将requirements.txt中的tensorflow这一项去掉，安装tensorflow1.4使用清华源，快一些，对应的cudnn是6.0版本

sudo pip3 install --upgrade https://mirrors.tuna.tsinghua.edu.cn/tensorflow/linux/gpu/tensorflow_gpu-1.4.0rc1-cp35-cp35m-linux_x86_64.whl

2、Keras用2.1就好，不能太高，会报错（pip3 install Keras==2.1）

3、pycocotools安装出现错误是Cython的原因，我的只能在python3上使用，所以把makefile里面的python改为了python3，python2上没有装上Cython....

4、将demo.ipynb转成了demo.py，放在和demo.ipynb相同的地方，使用VScode直接自动转换的。注释掉

# get_ipython().run_line_magic('matplotlib', 'inline')

不然会出错，这样应该就没有问题了，如果还有就应该是库版本的问题。

5、demo.py只能检测单张图像

如要检测视频或是调用摄像头可以使用下面这段代码

参考：https://www.youtube.com/watch?v=lLM8oAsi32g

扫描二维码关注公众号，回复： 5826395 查看本文章

import cv2
import numpy as np
 
def random_colors(N):
    np.random.seed(1)
    colors=[tuple(255*np.random.rand(3)) for _ in range(N)]
    return colors
 
def apply_mask(image, mask, color, alpha=0.5):
    """Apply the given mask to the image.
    """
    for n, c in enumerate(color):
        image[:, :, n] = np.where(
            mask == 1,
            image[:, :, n] *(1 - alpha) + alpha * c,
            image[:, :, n]
        )
    return image
 
def display_instances(image,boxes,masks,ids,names,scores):
    n_instances=boxes.shape[0]
    if not n_instances:
        print('No instances to display')
    else:
        assert boxes.shape[0] == masks.shape[-1] == ids.shape[0]
    
    colors=random_colors(n_instances)
    height, width = image.shape[:2]
    
    for i,color in enumerate(colors):
        if not np.any(boxes[i]):
            continue
        
        y1,x1,y2,x2=boxes[i]
        mask=masks[:,:,i]
        image=apply_mask(image,mask,color)
        image=cv2.rectangle(image,(x1,y1),(x2,y2),color,2)
        
        label=names[ids[i]]
        score=scores[i] if scores is not None else None
        
        caption='{}{:.2f}'.format(label,score) if score else label
        image=cv2.putText(
            image,caption,(x1,y1),cv2.FONT_HERSHEY_COMPLEX,0.7,color,2
        )
        
    return image
 
if __name__=='__main__':
    import os
    import sys
    import random
    import math
    import skimage.io
    import time
    import utils
    #import model as modellib
    
    
    ROOT_DIR = os.path.abspath("../")
    sys.path.append(ROOT_DIR)
    from mrcnn import utils
    import mrcnn.model as modellib
 
 
    sys.path.append(os.path.join(ROOT_DIR, "samples/coco/"))  # To find local version
    import coco
    
 
    MODEL_DIR = os.path.join(ROOT_DIR, "logs")
    COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")
    if not os.path.exists(COCO_MODEL_PATH):
        print('cannot find coco_model')
        
    class InferenceConfig(coco.CocoConfig):
        GPU_COUNT = 1
        IMAGES_PER_GPU = 1
 
    config = InferenceConfig()
    config.display()
    
    model = modellib.MaskRCNN(
        mode="inference", model_dir=MODEL_DIR, config=config
    )
 
    # Load weights trained on MS-COCO
    model.load_weights(COCO_MODEL_PATH, by_name=True)
    class_names = ['BG', 'person', 'bicycle', 'car', 'motorcycle', 'airplane',
               'bus', 'train', 'truck', 'boat', 'traffic light',
               'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird',
               'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear',
               'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie',
               'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
               'kite', 'baseball bat', 'baseball glove', 'skateboard',
               'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup',
               'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
               'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
               'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed',
               'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
               'keyboard', 'cell phone', 'microwave', 'oven', 'toaster',
               'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors',
               'teddy bear', 'hair drier', 'toothbrush']
    
    
    capture=cv2.VideoCapture(0)

    capture.set(cv2.CAP_PROP_FRAME_WIDTH,1920)
    capture.set(cv2.CAP_PROP_FRAME_HEIGHT,1080)

    size = (
        int(capture.get(cv2.CAP_PROP_FRAME_WIDTH)),
        int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
    )

    codec = cv2.VideoWriter_fourcc(*'DIVX')
    output = cv2.VideoWriter('./result/videofile_masked.avi', codec, 25.0, size)
    
    while True:
        ret,frame=capture.read()
        results=model.detect([frame],verbose=0)
        r=results[0]
        
        frame=display_instances(
              frame,r['rois'], r['masks'], r['class_ids'], 
                            class_names, r['scores']
        )
        
        output.write(frame)
        cv2.imshow('frame',frame)
        if cv2.waitKey(1)&0xFF==ord('q'):
            break
       
    capture.release()
    cv2.destroyAllWindows()

6、使用mask-rcnn检测人体姿态：https://blog.csdn.net/ghw15221836342/article/details/80617790

https://github.com/chrispolo/Keypoints-of-humanpose-with-Mask-R-CNN，这个用的是以前版本的masker-rcnn，直接下载使用就行。